Home

Volatility Measures for Regime Classification

Posted on May 14, 2026 By 
Regime detection and classification are important in portfolio management and asset allocation. One of the key inputs into regime detection models is volatility. Reference examines which volatility measure is most effective for regime classification. The authors study three volatility measures, Implied volatility (VIX/VIXBR), GARCH conditional volatility, Historical volatility. They …
Read More

Network Effects in Social Media Sentiment

Posted on May 6, 2026 By 
Social media sentiment has become increasingly important in modern portfolio and risk management. Most studies on social media rely on aggregate sentiment measures, such as average bullishness scores or overall positive-versus-negative comment ratios. Reference introduces an innovative approach to analyzing social media sentiment by investigating network effects, specifically how …
Read More

VIX Forecasting Using Crypto Overnight Returns

Posted on April 28, 2026 By 
Prediction is central in finance. A growing line of research uses cross-asset signals to forecast market movements. A recent example showed that Bitcoin can serve as a strong leading indicator in a machine learning-based trading system. Along similar lines, Reference examines whether cryptocurrency overnight returns, defined as price changes …
Read More

Regime-Aware Trading Strategies with Machine Learning

Posted on April 24, 2026 By 
Regime detection is important in portfolio management and remains an active area of research, particularly in the age of machine learning and AI. Reference proposes a trading strategy based on machine learning, combined with regime detection using a Hidden Markov Model. Specifically, the machine learning technique used is LightGBM, …
Read More

Gamma Exposure and S&P500 Return Predictability

Posted on April 20, 2026 By 
Options trading volume has been increasing rapidly, potentially altering market dynamics. Reference examines whether aggregate gamma exposure (GEX) in the S&P500 index options market contains predictive information about future equity returns and whether it can enhance short-term forecasting models. To do so, the authors construct an Autoregressive Distributed Lag …
Read More

Why Backtests Decay: Regime Dependence and Crowding

Posted on April 16, 2026 By 
Backtesting is an essential part of quantitative strategy development, and naturally, strategies are often selected based on strong backtest performance. However, an important question when evaluating backtested strategies is how much of the results reflects skill versus luck. Reference examines this issue by analyzing 1,726 commercially marketed strategies from …
Read More